Mark Winter
Mark Winter
**What this PR does / why we need it**: Currently the code assumes only one container in the `ServingRuntime`. This PR allows for multiple containers to be given in the...
/kind bug **What steps did you take and what happened:** When creating a Seldon MLServer to serve a LightGBM model, and using the storage spec, the env var `MLSERVER_LOAD_MODELS_AT_STARTUP` is...
Currently the website is only available at subpath `/website` https://kserve.github.io/website I think it would be better if it was under the rootpath `/` so it loads when visiting https://kserve.github.io Or...
Currently the Logs tab only shows logs for the `kserve-container`. For debugging it can be helpful to see the logs of other containers, especially the `storage-initializer`. The current Logs tab...
Currently when you click "New Model Server" it just lets you paste YAML. It would be nicer if it presented a form to create an Inference Service without YAML knowledge...
Currently it is not possible to edit existing model servers from the web app. This PR adds a new edit function that lets the users change the existing YAML. It...
Currently there is no activity in this repo. I have a good understanding of the code and am able to make significant updates to it (see my currently open PRs)....
/kind feature The web app currently seems to assume that grafana will be accessible via the same ingress as kubeflow under the path `/grafana`. We have a separated prometheus+grafana that...
It's pretty essential that all of the Itch message parsing has tests to ensure they're correct and any mistakes or typos are caught. This means testing both the Parse method,...
The ITCH implementation has been finished so it's nearly time to create the first versioned release. Before the release is created, tests should be added https://github.com/markwinter/go-finproto/issues/6 Potentially also finish soupbintcp...